Information processing device

Abstract

A processing device of an information processing device performs a search process including: a first step of calculating a relative frequency distribution of the original data; a second step of setting a plurality of time windows for clipping data of a partial period of the original data; a third step of clipping data from the original data; a fourth step of calculating a relative frequency distribution in the extracted data; and a fifth step of calculating an error between the relative frequency distribution in the original data and the relative frequency distribution in the extracted data, and a trial from the second step to the fifth step being repeatedly performed by changing the setting of the time windows. In the second step, the time windows are set such that the ratio between the periods before and after the specific maintenance become equal to that in the entire original data.

What is claimed is: 
     
         1 . An information processing device that reduces a volume of data to be used for analysis by extracting part of original data collected over a predetermined period using a plurality of sensors mounted on a vehicle, the information processing device comprising
 a processing device configured to perform a process, wherein   the processing device is configured to perform a search process,   the search process including a first step of calculating, for each of a plurality of features included in the original data, a relative frequency distribution in the original data, a second step of setting a plurality of time windows for clipping data of a partial period of the original data in such a manner that a sum of periods of all the time windows is shorter than the predetermined period, a third step of clipping data from the original data according to the time windows, a fourth step of calculating, for each of the features, the relative frequency distribution in extracted data obtained by combining all the data clipped according to the time windows, and a fifth step of calculating an error between the relative frequency distribution in the original data and the relative frequency distribution in the extracted data, and after the first step is performed, a trial from the second step to the fifth step being repeatedly performed by changing settings of the time windows, and the processing device performing the search process to extract the extracted data with the error equal to or less than a threshold value, and   the processing device is configured to set, in the second step, the time windows in such a manner that ratios between data before specific maintenance and data after the specific maintenance in an entirety of the original data and the extracted data are equal.   
     
     
         2 . The information processing device according to  claim 1 , wherein:
 the processing device is configured to perform clustering, the clustering being machine learning that groups data of each interval obtained by dividing the original data into intervals of a certain period into a predetermined number of clusters; and   the processing device is configured to set, in the second step, the time windows in such a manner that a difference between a proportion of each of the clusters in the extracted data and a proportion of each of the clusters in the entirety of the original data is equal to or less than a threshold value.   
     
     
         3 . The information processing device according to  claim 1 , wherein:
 the specific maintenance is an oil change;
 the original data includes data on a flow rate of oil as the feature; and 
 the processing device is configured to calculate an index value indicating a magnitude of damage accumulated in an oil filter by using the extracted data with the error equal to or less than the threshold value. 
   
     
     
         4 . The information processing device according to  claim 3 , wherein the processing device is configured to, when the calculated index value is equal to or greater than a predetermined value, notify that a failure is predicted to occur. 
     
     
         5 . The information processing device according to  claim 3 , wherein the processing device is configured to calculate the index value at predetermined time intervals and predict a service life of the oil filter from a slope of a change in the index value.